MFPNet: A Multi-scale Feature Propagation Network for Lightweight Semantic Segmentation

Guoan Xu, Wenjing Jia, Tao Wu, Ligeng Chen, Guangwei Gao

Abstract: In contrast to the abundant research focusing on large-scale models, the progress in lightweight semantic segmentation appears to be advancing at a comparatively slower pace. However, existing compact methods often suffer from limited feature representation capability due to the shallowness of their networks and the lack of feature guidance during the decoding process. In this paper, we propose a novel lightweight segmentation architecture, called Multi-scale Feature Propagation Network (MFPNet), to address the dilemma. Specifically, we design a robust Encoder-Decoder structure featuring symmetrical residual blocks that consist of flexible Bottleneck Residual Modules (BRMs) to explore deep and rich semantic context. Furthermore, taking benefit from their capacity to model latent long-range contextual relationships, we leverage Graph Convolutional Networks (GCNs) to facilitate multi-scale feature propagation between the BRM blocks. When evaluated on benchmark datasets, our proposed approach shows superior segmentation results.